{"id":"https://openalex.org/W2741325996","doi":"https://doi.org/10.18653/v1/d17-1272","title":"Counterfactual Learning from Bandit Feedback under Deterministic Logging : A Case Study in Statistical Machine Translation","display_name":"Counterfactual Learning from Bandit Feedback under Deterministic Logging : A Case Study in Statistical Machine Translation","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2741325996","doi":"https://doi.org/10.18653/v1/d17-1272","mag":"2741325996"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d17-1272","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1272","pdf_url":"https://www.aclweb.org/anthology/D17-1272.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D17-1272.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070442264","display_name":"Carolin Lawrence","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Carolin Lawrence","raw_affiliation_strings":["Heidelberg University, Germany","Heidelberg University, Heidelberg, Germany"],"affiliations":[{"raw_affiliation_string":"Heidelberg University, Germany","institution_ids":["https://openalex.org/I223822909"]},{"raw_affiliation_string":"Heidelberg University, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081885843","display_name":"Artem Sokolov","orcid":"https://orcid.org/0000-0002-8056-0504"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]},{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Artem Sokolov","raw_affiliation_strings":["Amazon Development Center & Heidelberg University, Germany","Amazon (United States), Seattle, United States"],"affiliations":[{"raw_affiliation_string":"Amazon Development Center & Heidelberg University, Germany","institution_ids":["https://openalex.org/I4210089985","https://openalex.org/I223822909"]},{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011749347","display_name":"Stefan Riezler","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Riezler","raw_affiliation_strings":["Heidelberg University, Germany","Heidelberg University, Heidelberg, Germany"],"affiliations":[{"raw_affiliation_string":"Heidelberg University, Germany","institution_ids":["https://openalex.org/I223822909"]},{"raw_affiliation_string":"Heidelberg University, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070442264"],"corresponding_institution_ids":["https://openalex.org/I223822909"],"apc_list":null,"apc_paid":null,"fwci":0.2694,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63591585,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2566","last_page":"2576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.933317244052887},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7311072945594788},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5388711094856262},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5304225087165833},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5041738748550415},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.479017436504364},{"id":"https://openalex.org/keywords/multiplicative-function","display_name":"Multiplicative function","score":0.4468400180339813},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.41696450114250183},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18521034717559814}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.933317244052887},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7311072945594788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5388711094856262},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5304225087165833},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5041738748550415},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.479017436504364},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.4468400180339813},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.41696450114250183},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18521034717559814},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/d17-1272","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1272","pdf_url":"https://www.aclweb.org/anthology/D17-1272.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1707.09118","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.09118","pdf_url":"https://arxiv.org/pdf/1707.09118","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2741325996","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1707.09118.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1707.09118","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1707.09118","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/d17-1272","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1272","pdf_url":"https://www.aclweb.org/anthology/D17-1272.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6052429835","display_name":null,"funder_award_id":"(DFG)","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2741325996.pdf","grobid_xml":"https://content.openalex.org/works/W2741325996.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W22168010","https://openalex.org/W1094752974","https://openalex.org/W1514587017","https://openalex.org/W1809653203","https://openalex.org/W1835900096","https://openalex.org/W2049934117","https://openalex.org/W2101105183","https://openalex.org/W2101234009","https://openalex.org/W2108738385","https://openalex.org/W2122124659","https://openalex.org/W2137387514","https://openalex.org/W2146574666","https://openalex.org/W2150291618","https://openalex.org/W2155607551","https://openalex.org/W2188353343","https://openalex.org/W2251912507","https://openalex.org/W2293743194","https://openalex.org/W2312609093","https://openalex.org/W2411447566","https://openalex.org/W2609616693","https://openalex.org/W2951403958","https://openalex.org/W2989631226"],"related_works":["https://openalex.org/W3121822496","https://openalex.org/W3034617946","https://openalex.org/W2532022121","https://openalex.org/W3131719136","https://openalex.org/W2964268110","https://openalex.org/W3005289089","https://openalex.org/W2073107347","https://openalex.org/W3174988439","https://openalex.org/W2735002392","https://openalex.org/W2755771904","https://openalex.org/W3126940024","https://openalex.org/W3025093529","https://openalex.org/W2964046129","https://openalex.org/W2948345763","https://openalex.org/W2885843666","https://openalex.org/W3006648316","https://openalex.org/W3021400604","https://openalex.org/W3035203794","https://openalex.org/W3127396816","https://openalex.org/W2111241577"],"abstract_inverted_index":{"The":[0,52],"goal":[1],"of":[2,22,54,57,112],"counterfactual":[3,68,73,119],"learning":[4,74,120],"for":[5,67],"statistical":[6],"machine":[7],"translation":[8],"(SMT)":[9],"is":[10,79],"to":[11,25,114],"optimize":[12],"a":[13],"target":[14],"SMT":[15,33,44,59],"system":[16],"from":[17,75,121],"logged":[18],"data":[19],"that":[20,27,41,72,99],"consist":[21],"user":[23],"feedback":[24],"translations":[26],"were":[28],"predicted":[29],"by":[30,38,82,93,118],"another,":[31],"historic":[32],"system.":[34],"A":[35],"challenge":[36],"arises":[37],"the":[39,48,58,64],"fact":[40],"riskaverse":[42],"commercial":[43],"systems":[45],"deterministically":[46],"log":[47],"most":[49],"probable":[50],"translation.":[51],"lack":[53],"sufficient":[55],"exploration":[56],"output":[60],"space":[61],"seemingly":[62],"contradicts":[63],"theoretical":[65],"requirements":[66],"learning.":[69,88],"We":[70],"show":[71,110],"deterministic":[76,85,122],"bandit":[77,123],"logs":[78],"possible":[80],"nevertheless":[81],"smoothing":[83],"out":[84],"components":[86],"in":[87,103],"This":[89],"can":[90],"be":[91],"achieved":[92],"additive":[94],"and":[95],"multiplicative":[96],"control":[97],"variates":[98],"avoid":[100],"degenerate":[101],"behavior":[102],"empirical":[104],"risk":[105],"minimization.":[106],"Our":[107],"simulation":[108],"experiments":[109],"improvements":[111],"up":[113],"2":[115],"BLEU":[116],"points":[117],"feedback.":[124]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}